skills.rest
zhaosj0315
zhaosj0315COMMUNITY
Explore all skills by this author →
WebsiteGitHub

add-voice-transcription

Transcribes WhatsApp voice notes into text using OpenAI Whisper in NanoClaw.

Updated Feb 5, 2026
Search Tags:#integration#OpenAI#transcription#whisper#voice-notes#WhatsApp#NanoClaw
One-click install
npx skills add https://github.com/zhaosj0315/nanoclaw --skill add-voice-transcription-zhaosj0315
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-voice-transcription
Source: https://github.com/zhaosj0315/nanoclaw/tree/main/.claude/skills/add-voice-transcription
Command: npx skills add https://github.com/zhaosj0315/nanoclaw --skill add-voice-transcription-zhaosj0315

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill transcribes voice messages in NanoClaw using OpenAI Whisper to convert spoken content into readable text for the agent.

Core Features & Use Cases

  • Transcribes incoming WhatsApp voice notes in registered groups to produce searchable, actionable transcripts for the agent.
  • Stores transcriptions in context so the agent can respond to voice content as it would to text messages.
  • Use Case: In a chat with a voice note from a colleague, the agent automatically converts it to text and replies with a summary or answer.

Quick Start

Install dependencies, build, and start:

  • npm install
  • npm run build
  • npm start

Frequently Asked Questions about add-voice-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe WhatsApp voice notes into text for my agent to read?▼

This skill transcribes WhatsApp voice notes by sending them to OpenAI Whisper via NanoClaw, converting the spoken audio into readable text that the agent can then process and respond to like a standard text message.

What do I need to set up to enable voice message transcription in NanoClaw?▼

Enabling voice message transcription requires adding an OpenAI API key for Whisper, setting up a configuration file, and running an npm build to activate the transcription pipeline for registered WhatsApp chats.

How does OpenAI Whisper integration work for processing voice messages?▼

OpenAI Whisper integration processes incoming WhatsApp voice messages by automatically converting the audio into searchable, actionable transcripts stored in the agent's context, enabling immediate responses to spoken content.

Can the agent automatically respond to WhatsApp voice notes using text transcription?▼

Yes, the agent automatically converts incoming WhatsApp voice notes to text using Whisper, stores the transcription in context, and can reply with a summary or answer based on the spoken content.

Which WhatsApp chats are supported for automatic voice transcription?▼

Automatic voice transcription supports WhatsApp voice notes received in registered chats and groups, converting the spoken audio content into text for the agent to read and act upon.

Related Skills

Explore More Software Engineering Skills→
b9b4ymiNb9b4ymiN

add-voice-transcription

please type here

Community
Advanced
dAAAbdAAAb
2

podcast-summarizer

Transcribe podcast episodes from Spotify, Apple Podcasts, and RSS feeds using Whisper.

Community
Intermediate
gunabotgunabot
7

setup

Automate NanoClaw installation, WhatsApp authentication, and channel registration.

Community
Advanced
kaivyykaivyy
20

Voice Skill

Transcribe audio files with OpenAI Whisper and synthesize speech from text.

Community
Intermediate